Pith. sign in

Paper Citation Record · LEDGER

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

As of 9 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2608.03506.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.03506 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:47:22.296113Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

66 of 66 outbound references displayed

  • verified exact0
  • verified fuzzy34
  • unresolved31
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a89525e4-611a-4bfb-8980-99d398d34ee0 · outbound

This paper cites The Eleventh International Conference on Learning Representations , year=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Eleventh International Conference on Learning Representations , year=

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:15.111765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:15.111765Z digest=sha256:625dee779545a4b0352ce055cf19b75908614267874876d66fe6e557e2812a23

Observation 2c07c816-0be5-4c5d-8f44-82f388e973b9 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:30.991369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.210678Z digest=sha256:7cb90d8a414f53f7b27420855a916f6be6477a44e7a7ff0f1c7ca2e62c28bdbf

Observation fc7966b0-818c-4562-808d-aa0c8b70c98a · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:15.266664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:15.266664Z digest=sha256:a327c3515dad3c9f1bfe2714a03abc884a5682f8740f9af2c9e85a8ce1b37d79

Observation f8c74186-9396-473d-878a-d48470418ac4 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Advances in Neural Information Processing Systems , volume=

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:30.663640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.358958Z digest=sha256:1cf98d3abe7a4ed31fc9defd4c02e59e0f2932a294d8c082b99616dbcf177b00

Observation fcc4a2a7-98c1-4144-b7a9-ce2b0d3ba660 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Twelfth International Conference on Learning Representations , year =

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:30.408732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.434370Z digest=sha256:6e2dc05079e88ac2b521478a207b43c6d2b3b41510fdbac86dbf9adad356b096

Observation 3609b8f4-fecd-485f-b003-f2b6ba9bc1e8 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:30.060981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.479624Z digest=sha256:6ffe68255dbb30ee39292c6c32c9ad186ded3822d49f5f3198f7bb47a1365de8

Observation 9d82915e-d022-42b6-b8b1-a49e8d6d9424 · outbound

This paper cites 2009 , publisher=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2009 , publisher=

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:15.598741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:15.598741Z digest=sha256:a607acc4c05a363f6d4f326010b767b7391632921c15ec46aaba8ec42aa34e66

Observation 10eee58e-5d40-46fe-8872-e15121b2b4d6 · outbound

This paper cites Scandinavian Journal of Statistics , volume=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Scandinavian Journal of Statistics , volume=

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:29.772770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.683050Z digest=sha256:5ed40fdda61dfea9ea5650eef29cb1cb58b89cc1d3a125f5c8c60497a52d908f

Observation 64bb93b5-21c3-46ca-9954-42db3564cfc4 · outbound

This paper cites Journal of Machine Learning Research , volume=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Journal of Machine Learning Research , volume=

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:29.527594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.762342Z digest=sha256:2d832027e085638ed48de71d3825e3b40d762ca834acc6b4f55b2ae95bf24e90

Observation 3ee62f8d-a40e-48df-be58-2831cd72a7c9 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Advances in Neural Information Processing Systems , volume=

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:15.837970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:15.837970Z digest=sha256:3e2f91e6045f2a37cb9e3f296b1207a8b21ef042577628ec822cf474af0f15d6

Observation d8ebb745-dad5-42b7-a640-41b9aaccde69 · outbound

This paper cites 2023 , publisher=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2023 , publisher=

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:29.234461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:15.946981Z digest=sha256:7e7b3fa866d923ecb10cefa76e338098504ef7e982b109591db52f7235fc793b

Observation 26ea4bfb-d4f6-47c8-a000-47618abb8d6f · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 12

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:28.935381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:16.042417Z digest=sha256:45dead554fc3b8bfb7917bf21e2acaf7d29cef293cd7b42c86650acd6e600898

Observation 3a5cc200-0106-42f5-8db6-0092b221732a · outbound

This paper cites Nature , volume=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Nature , volume=

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:16.074263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:16.074263Z digest=sha256:a268124684726ac4b2b3d5a1fd4efaf2917c4edab015ac311d1bb79190014194

Observation a6bb4ee4-94d3-4cf5-9b1e-1c59dc674e74 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Training Verifiers to Solve Math Word Problems

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:16.124276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:16.124276Z digest=sha256:9d1803e18b921b2d7af46959591eb7639e6554d9d413f71061b298aad729449c

Observation d767d588-09af-4b43-a674-53d918b6b991 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Solving math word problems with process- and outcome-based feedback

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:16.262287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:16.262287Z digest=sha256:e225669f91ce2a881192eeb3964108436ce9ccc9a694465fa448a9a888d826a6

Observation 9debf5a3-7efc-494d-b5aa-714bfd57cc30 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Twelfth International Conference on Learning Representations , year =

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:16.436571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:16.436571Z digest=sha256:249e8e0e63545fe5c34872b949aae8169194d4e38ffc5298bfb38bbf5885f775

Observation 3535523e-9e19-4f92-996e-61ff39185efd · outbound

This paper cites Math-Shepherd: Verify and Reinforce.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Math-Shepherd: Verify and Reinforce

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:16.590634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:16.590634Z digest=sha256:57ddfeb12841ae9b19a271d1a8509a2834dd9641a21dc7b843ef77725d12148c

Observation 994e31a4-4ed5-4a5f-a501-c5309150ec16 · outbound

This paper cites Uncovering Hidden Correctness in.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Uncovering Hidden Correctness in

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:28.701058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:16.814190Z digest=sha256:fa289adea0c6242f8239b3361715a132be427725f2b5b332512343d158cf3bbe

Observation a2e6ae64-a34a-4690-960c-3d6b935bd218 · outbound

This paper cites and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , booktitle=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , booktitle=

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:16.985175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:16.985175Z digest=sha256:c5237609057c372ee14810349089265db697e26f8ce653109a05710b1179adb3

Observation 2106e597-71fa-4633-9ce8-4716489d2552 · outbound

This paper cites 2022 , howpublished=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2022 , howpublished=

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:28.545483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:17.150213Z digest=sha256:d5147600e5cc36db4eeb163a55a3e1f0b0e7353f5ddb6c6f75d168fafb725390

Observation 40707b93-19e0-437e-b8a8-a57f58b95dda · outbound

This paper cites Is Best-of-.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Is Best-of-

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:28.463930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:17.239332Z digest=sha256:c3494aa783e9893bbf6bf69f7a07d213931a341a70b82079b76608e63297172f

Observation eaa4764a-f572-4655-a48b-1f1d213557e2 · outbound

This paper cites The Fourteenth International Conference on Learning Representations , year =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Fourteenth International Conference on Learning Representations , year =

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:28.314988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:17.357687Z digest=sha256:a06dfd0f2088baccb75352fac6960cc687487d28fa9c560cec2d669ed71ca92b

Observation 5976dc9f-af5a-4635-8c7e-60b526db540d · outbound

This paper cites 2017 , publisher=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2017 , publisher=

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:17.511298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:17.511298Z digest=sha256:9dd14cc056e38f680c6026eaaabc4c98f017784840fb573fa1212f9afa57ee39

Observation 5878f311-481b-4255-b081-e1e67fbe7fd0 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:28.157927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:17.618489Z digest=sha256:9fdfa66be9d3c359d2f1b7639abee3fc22e9507e24d44510a8990be5d919fadf

Observation d5aecfae-042c-4764-924e-88cc898dbc69 · outbound

This paper cites The Majority is not always right:.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Majority is not always right:

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:27.976472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:17.746013Z digest=sha256:9112492618c86c022beaa038e1a090198bd68b5d21ee304e4b0cd21436db56f5

Observation 50b7c363-6a49-4395-92f3-06f250235de4 · outbound

This paper cites 2026 , url=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2026 , url=

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:27.813448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:17.890680Z digest=sha256:3102da853b52e3bb83e132b335a624641e0b7818083f4e3ca677543991772173

Observation c79f280a-df16-4b24-94f6-e3cd843d52a8 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 27

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:27.681194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:18.064749Z digest=sha256:07371e3276daea6714b577630e4393514e3d7e2ee2059d4af11c29b211dc95e1

Observation 09d5b31e-c35b-45ef-8c72-9734ba484aef · outbound

This paper cites 2024 , howpublished=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2024 , howpublished=

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:27.498816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:18.183007Z digest=sha256:1d9cfb94f443cb428c815c31938fe64363ea5199f2f9d57d54f95d4999690e1d

Observation 007c2964-39f6-43f4-9f20-7a9bd413a0dc · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:18.343137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:18.343137Z digest=sha256:ce2b40f3b405397af5c19a266cc5ccbd757cc7046aeb8381ffc674570e60e27f

Observation c42a1aef-699d-4427-81c7-e0eba50e286b · outbound

This paper cites and Schult, Daniel A.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs and Schult, Daniel A

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:27.370660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:18.469411Z digest=sha256:28ab9e4984ac49681d9d8c6444178324a730fb14895b653dd0cf52623fd19019

Observation 25322e15-f045-419a-9776-5febe7dd22d6 · outbound

This paper cites International Conference on Learning Representations , year=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs International Conference on Learning Representations , year=

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:18.643787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:18.643787Z digest=sha256:d4bd63aa0a4bb595130181088db8954353ef00e3a2baaf10c5f8cdaae7f5f77f

Observation 9012d29b-4efe-44ba-8aca-46d7c8637607 · outbound

This paper cites Nature , volume=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Nature , volume=

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:18.757899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:18.757899Z digest=sha256:3dfdb0bad9946a61ad8209f06bd38d4cecbc4387dfaea8518093b810cb73e22b

Observation 581e1721-ed5c-4219-8c6a-9904aeee55f0 · outbound

This paper cites Universal Self-Consistency for Large Language Model Generation.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Universal Self-Consistency for Large Language Model Generation

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:18.895784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:18.895784Z digest=sha256:480a81bd3c96424d132990b1422f5fc8ecef0e10ed4a51251696eb54f50675d1

Observation f0e086c6-4413-440b-a3a1-9b8e6d354aa9 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:27.244271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.008164Z digest=sha256:7b216c623d746b305f2311bd4fa2e783d58685b151b92c1639fdd76865950047

Observation fdb81fc1-d970-4036-a50c-c7aa2ec429d1 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:27.044243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.081040Z digest=sha256:b73f3dd11c021063ebf99d3a507f4536b555fae2cb6e3776740ef819b78558c4

Observation 426ee1be-4950-423f-af2a-7eaba336e7d7 · outbound

This paper cites 2023 , publisher=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2023 , publisher=

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:26.840661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.157551Z digest=sha256:48236d0b5750667829eda4cd3a484508d53204bb195538d1ec4691c8681ae010

Observation 1fd2bc0d-5170-4a4d-a018-11dc2f17843a · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:19.236896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:19.236896Z digest=sha256:771373249deee9186b7f27828a634e6e46ecb186c94f1ebac12a776013b2ca91

Observation ac0b3327-f919-47f1-a409-445639b4ffeb · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages=

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:26.688056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.322591Z digest=sha256:4f40dfe591562afff7e5efb98e89c1b00ec9fe1a56c1a57433ddcaa129f92b3a

Observation 3df95f41-d2a9-4c17-b218-9fad2484c5b0 · outbound

This paper cites and Chen, Yatong and Cruz, Andr.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs and Chen, Yatong and Cruz, Andr

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:26.474973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.393826Z digest=sha256:e8b684d8246742b9b95be6849e3f99abeba13cc588c8302c2393cebcfa146d4b

Observation 6416a69b-691b-44dc-9473-4f9b334de09a · outbound

This paper cites The Fourteenth International Conference on Learning Representations , year =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Fourteenth International Conference on Learning Representations , year =

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:26.332352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.512055Z digest=sha256:adba1506a02b77066cf7f8a1dbb16b57fd6d1bf365193e509b4d31abb5e41803

Observation e3d61150-ca7d-4764-aa28-c5383aafc4d0 · outbound

This paper cites 2603.10624 , archivePrefix=.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2603.10624 , archivePrefix=

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:19.634404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:19.634404Z digest=sha256:6ec9334c591afc03ad26df493ade42f90a2cd17d9333cdad88f18d66b1840525

Observation 0b877e1e-2a39-42e0-af6b-d9b73e2b0e84 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:26.163178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:19.748671Z digest=sha256:b6f0bec4e80df4c2c4f5b6df3422c6d7aefd8d29f9d9fc9857c13e727a019ca1

Observation d73e25b3-41c0-4e5c-afc1-2f345600525c · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 43

Resolution
parse uncertain
no resolver link, observed 2026-08-05T17:47:19.834094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:19.834094Z digest=sha256:f21003a1fc0624345dd2a5956733e39a2817ec96a131765b2551b78dd5ba0e35

Observation 5f219c24-fa03-4cfb-9a75-4735a31a8142 · outbound

This paper cites Elements of Causal Inference: Foundations and Learning Algorithms , publisher =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Elements of Causal Inference: Foundations and Learning Algorithms , publisher =

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:19.915575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:19.915575Z digest=sha256:532c9ca40aec45082b313f28dd7edbd32b891c948e5feaca2f3fb641df90d0ae

Observation 8e961b88-01ff-4ad3-af72-fcb03174df09 · outbound

This paper cites Scandinavian Journal of Statistics , volume =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Scandinavian Journal of Statistics , volume =

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.995210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.014004Z digest=sha256:dbbfc2c8896517710f9b6aac18edbbd3c9eee6918d0386f3933d9e1c9235011a

Observation 0a893597-3298-413b-be32-009306188f40 · outbound

This paper cites Journal of Machine Learning Research , volume =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Journal of Machine Learning Research , volume =

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.820006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.090726Z digest=sha256:1ef1dd10b4ae8dbfadbf5b2f3ed6b548b7ca0f35eccc9c61d5f64a9116c32488

Observation 080ba491-021f-46e2-a14c-cda89d4ac539 · outbound

This paper cites Journal of the American Statistical Association , volume =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Journal of the American Statistical Association , volume =

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.679003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.207480Z digest=sha256:eae71533cf8c15b335927d42a17aa3292c5573316a3c0d0f7d1c080b7d5c51b7

Observation 0b70bb7e-bc53-4cbb-bbce-704d99eecbe9 · outbound

This paper cites and Schult, Daniel A.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs and Schult, Daniel A

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.519553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.289233Z digest=sha256:24c1077b92f87620cc37199b0043649f3b9a7735e622c52809e37e04ce4cee7a

Observation 6c1a0d7c-799e-4621-8a08-c59bc50110e4 · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2024 , pages =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Findings of the Association for Computational Linguistics: EMNLP 2024 , pages =

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.344457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.375206Z digest=sha256:d22d60ba7f3d6286eec200490a0281469409398adeb3c524d32da0e38ca8191d

Observation f869b7af-c2ab-4773-8195-05241c8af492 · outbound

This paper cites Journal of Statistical Software , volume =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Journal of Statistical Software , volume =

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.175622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.581378Z digest=sha256:f7cc4783168c62102ee644fb7066d5e4826b4880056c3be50a7cb5fdd970cb61

Observation 94dbb5aa-52cc-42fd-bcc2-1c8bc56a37a4 · outbound

This paper cites 2022 , howpublished =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2022 , howpublished =

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:25.081349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.712255Z digest=sha256:1ce1ab970fa8f666b45e786f2ba5856bc595d493325f2c3fd17c4c266d8d9796

Observation 492e2759-da7d-47ff-aabe-1502a75ae414 · outbound

This paper cites Advanced Intelligent Computing Technology and Applications (ICIC 2025) , series =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Advanced Intelligent Computing Technology and Applications (ICIC 2025) , series =

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:24.932827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.863607Z digest=sha256:064b0575a828cfcbdd042d11ef3f5d1957956f46150345c6b5084d1c74d49f5c

Observation 3b69a081-ab85-428c-ae8e-6adc63705b9f · outbound

This paper cites Findings of the Association for Computational Linguistics: NAACL 2025 , pages =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Findings of the Association for Computational Linguistics: NAACL 2025 , pages =

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:24.703843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:20.960161Z digest=sha256:ed523c4a52de0436e118b21bf51875c6f42b4a2b81b69cfc053264bdefac96a7

Observation 818a5de3-5a19-4d72-ab4a-341bc930bc83 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 54

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:24.560359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.032849Z digest=sha256:dcee57641efca2b8b92a264602a1c647836258738f70c679e98a85a56cd1b4a2

Observation 5322782f-4a65-413c-8c46-eb13feafbafd · outbound

This paper cites Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) , pages =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) , pages =

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:24.269526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.149816Z digest=sha256:2b15d29e3954093f3b1a0fd95607ac3a9a385f3351861f5c691943234368d166

Observation 560b0b32-d97e-4e68-b3b2-34c025378632 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Advances in Neural Information Processing Systems , volume =

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:24.024786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.280881Z digest=sha256:45d61f96b91fc7d2240550c2cca4727a8499684c4634cb8ab6490f8eb780964a

Observation 52051524-de69-4a0f-b5a4-7a4951863926 · outbound

This paper cites an unresolved cited work.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Unresolved cited work

Reference 57

Resolution
unresolved
raw_fallback, observed 2026-08-05T17:47:23.863830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.369801Z digest=sha256:bf30fbe57e8da587fe4bcc60b88ccea1828ed50e5eb0acb213988086e90502c8

Observation ac132236-2314-4a0e-bbd3-8bc72c5cf771 · outbound

This paper cites Qwen2.5 Technical Report.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Qwen2.5 Technical Report

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:21.484086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:21.484086Z digest=sha256:1e9320a966f1acf4bd9dc56bcf0cb0e185ee8f977a39a447cf4fc5b130b18783

Observation 04120ef0-1bed-46e3-b849-243f7a64963f · outbound

This paper cites 2024 , howpublished =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs 2024 , howpublished =

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:23.661103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.601309Z digest=sha256:8033e8cd2423bc5d8c5b3fee2409bebd7b6be518ea576a19d5b13c58782323aa

Observation 186f0923-e9d0-400b-baac-916bd0fad856 · outbound

This paper cites and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , title =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , title =

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:23.405425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.730725Z digest=sha256:f813090a7b1206d1ac596f40617c52dc9c72d0aee88e1ea0cba2c66052be9aad

Observation 557da700-adb2-4cc0-8037-bed0487132a4 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs Advances in Neural Information Processing Systems , volume =

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:23.238814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:21.836042Z digest=sha256:9cbed82aa53dc7ebdbb11c59cb40ea9cf5430dc2fab8fcb76822bdd93f55bc1f

Observation 062d5d2a-0276-4379-9c7b-bc9196ce57a3 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:21.960980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:21.960980Z digest=sha256:cc7c3620346e416f11b736e1ad2554228931976ee034254503bba4178fe43eeb

Observation 02a7d410-baaa-455d-a5d1-ee6c357f7959 · outbound

This paper cites The Fourteenth International Conference on Learning Representations , year =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Fourteenth International Conference on Learning Representations , year =

Reference 63

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:23.054120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:22.045029Z digest=sha256:301bc95f0ab6892ffcb430c10a23993267fa38dccc64f490783fb2101d84771b

Observation c4e31add-bd7c-47c0-8c6f-9d01ed1c5ff7 · outbound

This paper cites The Majority is not always right: RL training for solution aggregation.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Majority is not always right: RL training for solution aggregation

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-05T17:47:22.122408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T17:47:22.122408Z digest=sha256:f36a1e910c5b6611f89a69051909ded2ba598303dce0190f2cccd37a61dd172d

Observation b6fca671-fceb-4ce1-8f5b-d39759766014 · outbound

This paper cites , title =.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs , title =

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:22.835610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:22.207848Z digest=sha256:d90fbca3ab9c7290eebf4d030c955c905e2995986a6857eed656d9413546dede

Observation 6f0fd483-02a3-421c-a970-34975e91b01e · outbound

This paper cites and Chen, Yatong and Cruz, Andr.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs and Chen, Yatong and Cruz, Andr

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T17:47:22.637585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-05T17:47:22.296113Z digest=sha256:7357c116e046aa734aff3524e7eec7667beeae2faa025d6ab1956d5468984188

Pith citing papers

No inbound Pith citation observations are available.